arXiv AI
Jun 10
Support sufficiency as action-sufficient compression: a single-cycle rate-regret formulation
arXiv:2606. 09858v1 Announce Type: cross Abstract: Robust decision-making requires compression.
SCAMP: Sparse-anchor Control is One Small Projection
SCAMP introduces a training‑free, damped Gauss‑Newton method that adjusts only the sparse anchor points in a frozen differentiable decoder, keeping the rest of the state unchanged. By operating solely in the space of the anchors’ Jacobian rows, it solves a system whose size matches the number of anchor constraints rather than the full state, enabling efficient control across diverse text‑to‑motion generators. Applied to seven existing generators, SCAMP achieves anchor errors that match or surpass all released control methods and can close anchors on hosts that originally lacked them.
Related stories
arXiv Machine Learning
Aug 17
Friction-Augmented Drifting Models for Resource-Efficient Domain Translation
arXiv:2604. 18194v2 Announce Type: replace Abstract: Single-step generators promise high-fidelity synthesis at a fraction of the inference and training cost of ordinary differential equation (ODE)-based flow models, a central concern when compute is limited.
arXiv Machine Learning
Sep 17
The Automaton Underneath: The Additive Input Pathway Is a Parasitic Attractor for State Tracking in Householder Linear RNN
arXiv:2609. 18966v1 Announce Type: new Abstract: Linear RNNs with input-dependent Householder-product transitions (DeltaNet/DeltaProduct-class) can provably represent hard state-tracking automata, yet trained models fail to length-generalize -- a gap recent work attributes to optimization, without a causal account.
arXiv Machine Learning
Aug 27
Drift Variation Autoencoder: Unifying Generation and Representation Learning through Conditional Posterior Flow Matching
arXiv:2608. 25138v1 Announce Type: new Abstract: Stochastic masking, cropping, or modality removal makes deterministic reconstruction an incomplete target: one observation can admit many clean completions.
arXiv AI
Jun 10
Structure from Reasoning, Numbers from Search: On-Premise Open LLMs as Structural Priors for Coupled MIMO Controller Tuning
arXiv:2606. 11015v1 Announce Type: new Abstract: Tuning controllers for strongly coupled multi-input multi-output (MIMO) industrial processes is hard: decentralized classical auto-tuning ignores loop interaction, and local numerical optimization from natural initializations stalls in the resulting non-convex cost landscape.
arXiv AI
2d ago
Measuring the Stability Assumption Behind Action Chunking
The paper investigates how small action errors evolve when using action chunking in behavioural cloning. By injecting errors at each state and observing their growth under open‑loop (no replanning) and closed‑loop (replanning) regimes, the authors classify states as contracting, expanding, or unresolved. Across twelve manipulation tasks, they find that stable states are rare, error amplification is common, and that short‑horizon fitting can overestimate long‑horizon propagation. Predictors trained on camera and proprioceptive data can recover open‑loop stability but only partially capture closed‑loop dynamics, indicating that standard imitation learning does not reliably produce policies that contract errors when perturbed.
arXiv AI
Jul 29
Context Assembly as the Controlled Variable: A Control-Theoretic View of Harness Policies for Frozen LLM Agents
arXiv:2607. 25408v1 Announce Type: new Abstract: A growing body of 2026 work applies control theory to LLM agents: Lyapunov-certified stability for tool-mediated controllers (Prinos et al.
arXiv AI
Jul 29
$\pi\mathbf{R}^2$: Reactive Real-time Flow Policies
arXiv:2607. 26055v1 Announce Type: cross Abstract: Generalist manipulation policies increasingly take the form of action-chunking flow policies built on large pretrained backbones.
arXiv Machine Learning
Sep 15
Learned Bow Control on a Measured Bowed-String Model: a Revised Minimum-Bow-Force Law, a Recurrent Controller, and the Domain of a Supervision Ceiling
arXiv:2609.14990v1 Announce Type: cross Abstract: A finite-difference bowed-string model with implicitly resolved Stribeck friction is presented, with a regime diagnostic, the Schelleng bow-force lim...
arXiv AI
Jun 9
Polynomial Context-Truncation Sensitivity in Autoregressive Language Models: Sequential Wyner-Ziv Bounds for KV Cache Compression
arXiv:2605. 25085v2 Announce Type: replace-cross Abstract: We study the rate-distortion limits of online KV cache compression in autoregressive language models, formulating it as sequential Wyner-Ziv source coding on the filtration induced by the model, with the next-step query as decoder side information.
arXiv Machine Learning
Aug 17
Consistent Model Chasing Is Minimax Optimal: The Exact Value of Scalar Adversarial Adaptive Control under Large Parametric Uncertainty
arXiv:2608. 13651v1 Announce Type: cross Abstract: We solve exactly a fundamental problem of adaptive control against adversarial disturbances: regulate the scalar system $x_{t+1} = ax_t + u_t + w_t$, $x_0=0$, $\|w\|_\infty \le 1$, where the constant pole $a \in [-\Delta, \Delta]$ is unknown in sign and magnitude and $\Delta$ is arbitrarily large.
arXiv AI
Sep 25
Operator Packages, Proposer Strength, and Construction-Family Plateaus in Office-Scale Verified Search
The paper reports on a large‑scale verified search experiment using a 30B language model on a laptop, evaluating three operator packages—schematic notebooks, named obstacles, and behavioural repulsion—in a factorial design across nine construction problems. Results show that the full composition of operators closes the seed‑to‑record gap more effectively than any single component, increases construction‑hash diversity, and that memory plus repulsion consistently avoids collapse. A frontier proposer achieves similar gains in far fewer samples, but the search ultimately stalls near a plateau where the reference family is adopted and optimized only when provided as code.